Evaluation of fuzzy-based classifiers for cotton crop identification

In this study, an evaluation of fuzzy-based classifiers for specific crop identification using multi-spectral temporal data spanning over one growing season has been carried out. The temporal data sets have been georeferenced with 0.3 pixel rms error. Temporal information of cotton crop has been incorporated through the following five indices: simple ratio (SR), normalized difference vegetation index (NDVI), transformed normalized difference vegetation index (TNDVI), soil-adjusted vegetation index (SAVI) and triangular vegetation index (TVI), to study the effect of indices on classified output. For this purpose, a comparative study between two fuzzy-based soft classification approaches, possibilistic c-means (PCM) and noise classifier (NC), was undertaken. In this study, advanced wide field sensor (AWiFS) data for soft classification and linear imaging self scanner sensor (LISS III) data for soft testing purpose from Resourcesat-1 (IRS-P6) satellite were used. It has been observed that NC fuzzy classifier using TNDVI temporal index – dataset 2, which comprises four temporal images performs better than PCM classifier giving highest fuzzy overall accuracy of 96.03%.     

光谱指数趋势面的城市地表温度降尺度转换

针对城市及周边区域建造区和自然地表交织分布的特点,探讨了利用归一化植被指数(NDVI)和归一化建造指数(NDBI)构造趋势面的地表温度(LST)降尺度方法,以北京市市区及周边较平坦区域为例实现了LST自960 m向120 m的降尺度转换。分析了LST空间分布特征及NDVI、NDBI对地物的指示性特征;以北京市四至六环为界分析NDVI、NDBI趋势面对地表温度的拟合程度及各自的适用区域;在120 m、240 m、480 m和960 m 4个尺度上评价了NDVI、NDBI和NDVI+NDBI趋势面对LST的拟合程度和趋势面转换函数的尺度效应;对NDVI、NDBI和NDVI NDBI等3种方法的降尺度结果分覆盖类型、分区域对比评价。实验结果表明结合两种光谱指数的NDVI NDBI方法降尺度转换精度有所改善,改善程度取决于地表覆盖类型组合。     

Liquefaction Identification Using IRS-1D Temporal Indices Data

One of the major after effect of Bhuj Earthquake which occurred on January 26, 2001 was wide spread appearance of liquefaction of soil in the Rann of Kachchh and the coastal areas of Kandla port covering an area of more than tens of thousands of kilometers. Remote sensing data products allow us to explore the land surface parameters at different spatial scales. In this work, an attempt has been made to identify the liquefied soil area using conventional indices from IRS-1D temporal images. The same has been investigated and compared with Class Based Sensor Independent (CBSI) spectral indices, while applying fuzzy based noise classification as soft computing approach using supervised classification. Seven spectral indices have been investigated to identify liquefied soil areas using temporal multi-spectral images. The result shows that the temporal variations can be accounted by using appropriate remote sensing based spectral indices. It is found that CBSI based TNDVI using temporal data yields the best results for identification of liquefied soil areas, while CBSI based SR gives best results for water body identification.     

Temporal MODIS data for identification of wheat crop using noise clustering soft classification approach

In this study, temporal MODIS-Terra MOD13Q1 data have been used for identification of wheat crop uniquely, using the noise clustering (NC) soft classification approach. This research also optimises the selection of date combination and vegetation index for classification of wheat crop. First, a separability analysis is used to optimise the date combination for each case of number of dates and vegetation index. Then, these scenes have undergone for NC soft classification. The resolution parameter (δ) was optimised for the NC classifier and found to be a value of 1.6 × 10⁴ for wheat crop identification. Classified outputs were analysed by receiver operating characteristics (ROC) analysis for sub-pixel detection. Highest area under the ROC curve was found for soil-adjusted vegetation index corresponding to the three different phenological stages data sets. From this study, the data sets corresponding to the Sowing, Flowering and Maturity phenological stages of wheat crop were found more suitable to identify it uniquely.     

Mapping a Specific Crop—A Temporal Approach for Sugarcane Ratoon

Mapping a specific crop using single date multi-spectral imagery remains a challenging task because vegetation spectral responses are considerably similar. The use of multi-temporal images helps to discriminate specific crops as the classifier can make use of the uniqueness in the temporal evolution of the spectral responses of the different vegetated classes. However, one major concern in multi-temporal studies is the selection of optimum dates for the discrimination of crops as the use of all available temporal dates can be counterproductive. In this study this concern was addressed by selecting the best 2, 3, 4… combinations dates. This was done by conducting a separability analysis between the spectral response of the class of interest (here, sugarcane-ratoon) and non-interest classes. For this analysis, we used time series LISS-III and AWiFS sensors data that were classified using Possibilistic c-Means (PCM). This fuzzy classifier can extract single class sub-pixel information. The end result of this study was the detection of best (optimum) temporal dates for discriminating a specific crop, sugarcane-ratoon. An accuracy of 92.8 % was achieved for extracting ratoon crop using AWiFS data whereas the optimum temporal LISS-III data provided a least entropy of 0.437. Such information can be used by agricultural department in selecting an optimum number of strategically placed temporal images in the crop growing season for discriminating the specific crop accurately.     

Monitoring growth of built-up areas in indo-gangetic plain using multi-sensor remote sensing data

This paper provides an approach for rapid and accurate estimation of built-up areas on a per pixel-basis using a integration of two coarse spatial resolution remote sensing data namely DMSP-OLS and MODIS NDVI. The DMSP-OLS data due to its free availability, high temporal resolution and wide swath was used for regional level mapping of built-up areas. However, due to its low radiometric resolution, the built-up areas cannot be estimated accurately from the DMSP-OLS data. In present study, the DMSP-OLS data was combined with MODIS NDVI data to develop an Human Settlement Index (HSI) image, which estimated the fraction of built-up area on a per pixel basis. The resultant HSI image conveys more information than both the individual datasets. These temporal HSI images were then used for monitoring urban growth in Indo-Gangetic plains during the 2001–2007 time period. Thus, the present research can be very useful for regional level monitoring of built-up areas from coarse resolution data within limited time and minimal cost.     

Wheat Monitoring by Using Kernel Based Possibilistic <Emphasis Type="Italic">c</Emphasis>-Means Classifier: Bi-sensor Temporal Multi-spectral Data

The existence of mixed pixels in the satellite images has always been an area of concern. Adding to the challenge is an occurrence of non-linearity between the classes, which is generally overlooked. The study makes an attempt to solve the two frequently occurring problems by kernel based fuzzy approach. This research work deals with Possibilistic c-Means (PCM) classifier with local, global, spectral angle and hyper tangent kernels for wheat crop (Triticum aestivum) identification in Haridwar, Uttarakhand, India. The multi-temporal vegetation index data of Formosat-2 have been used which covers the whole phenology of wheat crop. The additional sensor Landsat-8 OLI imagery has been filled the crucial gap of Formosat-2 temporal datasets. Nine types of proposed kernels based PCM classifier have been applied on three temporal datasets (four, five and six date combinations) to classify two classes early sown and late sown wheat crop. These test results have been concluded that at optimized weighted constant KMOD and polynomial kernel was found effective to separate wheat crop. The five and six date combination were sufficient to discriminate early sown and late sown wheat crop.     

Fuzzy Based Approach for Moist Deciduous Forest Identification Using MODIS Temporal Data

Fuzzy based soft classification have been used immensely for handling the mixed pixel and hence to extract the single class of interest. The present research attempts to extract the moist deciduous forest from MODIS temporal data using the Possibilistic c-Means (PCM) soft classification approach. Temporal MODIS (7 dates) data were used to identify moist deciduous forest and temporal AWiFS (7 dates) data were used as reference data for testing. The Simple Ratio (SR), Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI), and Transformed Normalized Difference Vegetation Index (TNDVI) were used to generate the temporal vegetation indices for both the MODIS and the AWiFS datasets. It was observed from the research that the MODIS temporal NDVI data set1, which contain the minimum number of images and avoids the temporal images corresponding to the highest frequency stages of onset of greenness (OG) and end of senescence (ES) activity of moist deciduous forest have been found most suitable data set for identification of moist deciduous forest with the maximum fuzzy overall accuracy of 96.731 %.     

A new spectral index for the extraction of built-up land features from Landsat 8 satellite imagery

Abstract

Extracting built-up areas from remote sensing data like Landsat 8 satellite is a challenge. We have investigated it by proposing a new index referred as built-up land features extraction index (BLFEI). The BLFEI index takes advantage of its simplicity and good separability between the four major component of urban system, namely built-up, barren, vegetation and water. The histogram overlap method and the spectral discrimination index (SDI) are used to study separability. BLFEI index uses the two bands of infrared shortwaves, the red and green bands of the visible spectrum. OLI imagery of Algiers, Algeria, was used to extract built-up areas through BLFEI and some new previously developed built-up indices used for comparison. The water areas are masked out leading to Otsu’s thresholding algorithm to automatically find the optimal value for extracting built-up land from waterless regions. BLFEI, the new index improved the separability by 25% and the accuracy by 5%.     

基于TM图像的“增强的指数型建筑用地指数”研究

以Landsat TM/ETM+图像为数据源,研究城镇和农村建筑用地信息的提取方法.首先利用TM7,4,2波段创建归一化差值裸地与建筑用地指数(normalized difference bareness and built- up index,NDBBI);然后根据裸地在裸土指数(bare doil index,BSI)图像上的亮度值最高、在改进型归一化差值水体指数(modified normalized difference water index,MNDWI)图像的亮度值最低的特征,提出了增强型裸土指数(enhanced baresoilindex,EBSI);最后选用NDBBI,EBSI,MNDWI和SAVI( soil adjustment vegetation index,SAVI)4个指数,构建一种新型的建筑用地指数,称为“增强的指数型建筑用地指数”( enhanced index - based built - up index,EIBI),可快速地提取建筑用地信息.实验结果表明,用EIBI提取的建筑用地信息客观,人为干预少,可信度高,提取精度可达90％以上,适合于同时提取城市和农村建筑用地信息.     

Analyzing fine-scale wetland composition using high resolution imagery and texture features

In order to monitor natural and anthropogenic disturbance effects to wetland ecosystems, it is necessary to employ both accurate and rapid mapping of wet graminoid/sedge communities. Thus, it is desirable to utilize automated classification algorithms so that the monitoring can be done regularly and in an efficient manner. This study developed a classification and accuracy assessment method for wetland mapping of at-risk plant communities in marl prairie and marsh areas of the Everglades National Park. Maximum likelihood (ML) and Support Vector Machine (SVM) classifiers were tested using 30.5 cm aerial imagery, the normalized difference vegetation index (NDVI), first and second order texture features and ancillary data. Additionally, appropriate window sizes for different texture features were estimated using semivariogram analysis. Findings show that the addition of NDVI and texture features increased classification accuracy from 66.2% using the ML classifier (spectral bands only) to 83.71% using the SVM classifier (spectral bands, NDVI and first order texture features).     

An improved building detection approach using L-band POLSAR two-dimensional time-frequency decomposition over oriented built-up areas

The objective of this study is to efficiently extract detailed information about various man-made targets in oriented built-up areas using polarimetric synthetic aperture radar (POLSAR) images. This paper develops an improved approach for building detection by utilizing Two-Dimensional Time-Frequency (2-D TF) decomposition. This method performs outstandingly in distinguishing between man-made and natural targets based on the isotropic behaviors, frequency-sensitive responses, and scattering mechanisms of objects. The proposed method can preserve the spatial resolution and exploit the advantages of TF decomposition; specifically, the exact outlines of buildings can be effectively located, and more types of features (e.g., flat roofs, roads, and walls that are oblique to the radar illumination) can be distinguished from forests in complex built-up areas by 2-D TF decomposition. The coarser-resolution subaperture images that are produced in the azimuth direction, which correspond to different looking angles, are beneficial for detecting man-made structures with main scattering centers oriented at oblique angles with respect to the radar illumination. In the range direction, the obtained subaperture images, which correspond to various observation frequencies, can be helpful in distinguishing flat roofs and roads from forests. This method was successfully implemented to analyze both NASA/JPL L-band AIRSAR and L-band EMISAR data sets. The building detection results of the proposed method exhibit a significant improvement over those of other methods and reach an overall accuracy over 80%, with approximately 20% higher than the accuracies of K-means clustering and the entropy/alpha-Wishart classifier and approximately 10% higher than the accuracy of the support vector machine method. Moreover, building details can be precisely detected, obliquely oriented buildings can be identified, and the distinction between buildings and forests is significantly improved, as both visually and statistically indicated. This method is highly adaptable and has substantial application value.     

Multiple spectral similarity metrics for surface materials identification using hyperspectral data

Modern hyperspectral imaging and non-imaging spectroradiometer has the capability to acquire high-resolution spectral reflectance data required for surface materials identification and mapping. Spectral similarity metrics, due to their mathematical simplicity and insensitiveness to the number of reference labelled spectra, have been increasingly used for material mapping by labelling reflectance spectra in hyperspectral data labelling. For a particular hyperspectral data set, the accuracy of spectral labelling depends considerably upon the degree of unambiguous spectral matching achieved by the spectral similarity metric used. In this work, we propose a new methodology for quantifying spectral similarity for hyperspectral data labelling for surface materials identification. Developed adopting the multiple classifier system architecture, the proposed methodology unifies into a single framework the differential performances of eight different spectral similarity metrics for the quantification of spectral matching for surface materials. The proposed methodology has been implemented on two types of hyperspectral data viz. image (airborne hyperspectral images) and non-image (library spectra) for numerous surface materials identification. Further, the performance of the proposed methodology has been compared with the support vector machines (SVM) approach, and with all the base spectral similarity metrics. The results indicate that, for the hyperspectral images, the performance of the proposed methodology is comparable with that of the SVM. For the library spectra, the proposed methodology shows a consistently higher (increase of about 30% when compared to SVM) classification accuracy. The proposed methodology has the potential to serve as a general library search method for materials identification using hyperspectral data.     

Urban growth analysis using spatial and temporal data

Urban growth identification, quantification, knowledge of rate and the trends of growth would help in regional planning for better infrastructure provision in environmentally sound way. This requires analysis of spatial and temporal data, which help in quantifying the trends of growth on spatial scale. Emerging technologies such as Remote Sensing, Geographic Information System (GIS) along with Global Positioning System (GPS) help in this regard. Remote sensing aids in the collection of temporal data and GIS helps in spatial analysis. This paper focuses on the analysis of urban growth pattern in the form of either radial or linear sprawl along the Bangalore — Mysore highway. Various GIS base layers such as built-up areas along the highway, road network, village boundary etc. were generated using collateral data such as the Survey of India toposheet, etc. Further, this analysis was complemented with the computation of Shannon’s entropy, which helped in identifying prevalent sprawl zone, rate of growth and in delineating potential sprawl locations. The computation Shannon’s entropy helped in delineating regions with dispersed and compact growth. This study reveals that the Bangalore North and South taluks contributed mainly to the sprawl with 559% increase in built-up area over a period of 28 years and high degree of dispersion. The Mysore and Srirangapatna region showed 128% change in built-up area and a high potential for sprawl with slightly high dispersion. The degree of sprawl was found to be directly proportional to the distances from the cities.     

Road condition assessment by OBIA and feature selection techniques using very high-resolution WorldView-2 imagery

Accurate information on the conditions of road asphalt is necessary for economic development and transportation management. In this study, object-based image analysis (OBIA) rule-sets are proposed based on feature selection technique to extract road asphalt conditions (good and poor) using WorldView-2 (WV-2) satellite data. Different feature selection techniques, including support vector machine (SVM), random forest (RF) and chi-square (CHI) are evaluated to indicate the most effective algorithm to identify the best set of OBIA attributes (spatial, spectral, textural and colour). The chi-square algorithm outperformed SVM and RF techniques. The classification result based on CHI algorithm achieved an overall accuracy of 83.19% for the training image (first site). Furthermore, the proposed model was used to examine its performance in different areas; and it achieved accuracy levels of 83.44, 87.80 and 80.26% for the different selected areas. Therefore, the selected method can be potentially useful for detecting road conditions based on WV-2 images.     

Step-wise Land-class Elimination Approach for extracting mixed-type built-up areas of Kolkata megacity

The extraction of urban built-up areas is an important aspect of urban planning and understanding the complex drivers and biophysical mechanism of urban climate processes. However, built-up area extraction using Landsat data is a challenging task due to spatio-temporal dynamics and spatially intermixed nature of Land Use and Land Cover (LULC) in the cities of the developing countries, particularly in tropics. In the light of advantages and drawbacks of the Normalized Difference Built-up Index (NDBI) and Built-up Area Extraction Method (BAEM), a new and simple method i.e. Step-wise Land-class Elimination Approach (SLEA) is proposed for rapid and accurate mapping of urban built-up areas without depending exclusively on the band specific normalized indices, in order to pursue a more generalized approach. It combines the use of a single band layer, Normalized Difference Vegetation Index (NDVI) image and another binary image obtained through Logit model. Based on the spectral designation of the satellite image in use, a particular band is chosen for identification of water pixels. The Double-window Flexible Pace Search (DFPS) approach is employed for finding the optimum threshold value that segments the selected band image into water and non-water categories. The water pixels are then eliminated from the original image. The vegetation pixels are similarly identified using the NDVI image and eliminated. The residual pixels left after elimination of water and vegetation categories belong either to the built-up areas or to bare land categories. Logit model is used for separation of the built-up areas from bare lands. The effectiveness of this method was tested through the mapping of built-up areas of the Kolkata Metropolitan Area (KMA), India from Thematic Mapper (TM) images of 2000, 2005 and 2010, and Operational Land Imager (OLI) image of 2015. Results of the proposed SLEA were 95.33% accurate on the whole, while those derived by the NDBI and BAEM approaches returned an overall accuracy of 83.67% and 89.33%, respectively. Comparisons of the results obtained using this method with those obtained from NDBI and BAEM approaches demonstrate that the proposed approach is quite reliable. The SLEA generates new patterns of evidence and hypotheses for built-up areas extraction research, providing an integral link with statistical science and encouraging trans-disciplinary collaborations to build robust knowledge and problem solving capacity in urban areas. It also brings landscape architecture, urban and regional planning, landscape and ecological engineering, and other practice-oriented fields to bear together in processes for identifying problems and analyzing, synthesizng, and evaluating desirable alternatives for urban change. This method produced very accurate results in a more efficient manner compared to the earlier built-up area extraction approaches for the landscape and urban planning.     

地面成像光谱数据的田间杂草识别

地面成像光谱数据兼具高光谱分辨率与高空间分辨率,在田间杂草识别中具有很好的应用前景。目前基于机器视觉的杂草识别方法以形状特征为主,当作物杂草形态相似时识别的困难和利用高光谱特征以像元为单元识别时效率较低,不利于实时自动化除草,因此,本文提出一种综合面向对象与高光谱特征匹配的杂草识别方法,在对作物杂草对象样本的形状特征和光谱曲线提取分析的基础上,建立基于形状特征规则与光谱角匹配的植物对象识别决策树,用于识别实验田中的作物杂草对象。实验结果表明,当场景中某些不同种类植物对象的形态相似时,基于形状特征规则与光谱角匹配的杂草识别方法可借助高光谱特征精细区分植物对象的种类,且在形状特征规则约束下使用高光谱特征匹配法识别植物对象,可克服"同物异谱"和"同谱异物"现象带来的不确定性,该方法识别精度可优于仅使用光谱角匹配法的情况,并优于使用颜色和形状分析技术的情况。     

基于反射光谱预测土壤重金属元素含量的研究

本文利用实验室实测的土壤反射光谱以及铅、镉、汞等重金属元素数据,进行土壤重金属元素含量快速预测的可行性研究。本文利用偏最小二乘回归方法,研究了反射率(R)、一阶微分(FDR)、反射率倒数的对数(lg(1/R))和波段深度(BD)等对预测精度的影响,对这几种光谱指标预测土壤重金属含量的能力进行了分析和评价,同时分析了多光谱数据估算土壤重金属元素含量的可行性。结果表明,反射率倒数的对数lg(1/R)是估算土壤重金属元素含量最好的光谱指标,尤其是Cd和Pb,检验精度R超过0.82。有机质、铁锰氧化物和黏土矿物对土壤重金属元素的吸附是可见光—近红外—短波红外光谱估算其含量的机理。多光谱数据同样具有估算土壤重金属元素含量的能力,但实际数据则要考虑多种因素的影响。     

Evaluation of multisource data for glacier terrain mapping: a neural net approach

Spectrally similar nature of land covers in a glacierized terrain hampers their automated mapping from multispectral satellite data, which may be overcome by using multisource data. In the present study, an artificial neural network (ANN)-based information extraction approach was applied for mapping the Kolahoi glacier and adjoining areas, using Landsat TM (Thematic Mapper) data and several ancillary layers such as image transformations and topographic attributes. Results reveal that ANN (highest overall accuracy (OA): 83.74%) outperforms maximum likelihood classifier (highest OA: 66.90%) and the incorporation of ancillary data into the classification process significantly enhances the mapping accuracy (>9%), particularly the addition of Near Infrared Red/Short Wave Infrared (NIR/SWIR) data to the spectral data. A nine-band combination dataset (spectral data, slope, Red/NIR and decorrelation stretch) was found to be the best multisource dataset. Results of the Z-tests (at 95% confidence level) also corroborate and statistically validate the above findings.     

RNDSI: A ratio normalized difference soil index for remote sensing of urban/suburban environments

Understanding land use land cover change (LULCC) is a prerequisite for urban planning and environment management. For LULCC studies in urban/suburban environments, the abundance and spatial distributions of bare soil are essential due to its biophysically different properties when compared to anthropologic materials. Soil, however, is very difficult to be identified using remote sensing technologies majorly due to its complex physical and chemical compositions, as well as the lack of a direct relationship between soil abundance and its spectral signatures. This paper presents an empirical approach to enhance soil information through developing the ratio normalized difference soil index (RNDSI). The first step involves the generation of random samples of three major land cover types, namely soil, impervious surface areas (ISAs), and vegetation. With spectral signatures of these samples, a normalized difference soil index (NDSI) was proposed using the combination of bands 7 and 2 of Landsat Thematic Mapper Image. Finally, a ratio index was developed to further highlight soil covers through dividing the NDSI by the first component of tasseled cap transformation (TC1). Qualitative (e.g., frequency histogram and box charts) and quantitative analyses (e.g., spectral discrimination index and classification accuracy) were adopted to examine the performance of the developed RNDSI. Analyses of results and comparative analyses with two other relevant indices, biophysical composition index (BCI) and enhanced built-up and bareness Index (EBBI), indicate that RNDSI is promising in separating soil from ISAs and vegetation, and can serve as an input to LULCC models.